Date of Award

12-2022

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Industrial-Organizational Psychology

Committee Chair/Advisor

Patrick J. Rosopa

Committee Member

Marissa L. Shuffler

Committee Member

Fred S. Switzer

Committee Member

Emily L. Hirsh

Abstract

Given the complex (Ratnapalan & Lang, 2020) and high stress environment of healthcare organizations (Freshwater & Cahill, 2010), a better understanding of the conditions in which healthcare professionals work is important. Although previous research has resulted in somewhat limited categories of the demands on healthcare professionals (Borteyrou et al., 2014; Shanafelt et al., 2020), a comprehensive taxonomy that covers the breadth and depth of demands is lacking. Using longitudinal data collected over 28 measurement waves spanning two years during the COVID-19 pandemic, the present studies outline the development of a taxonomy based on an in-depth literature review of related workplace models and taxonomies (Britannica, n.d.; Du Toit et al., 2003; Liu et al., 2018; Shirom & Melamed, 2006; Shoss, 2017; World Health Organization, 2021), 22,500+ qualitative comments from emergency medicine clinicians, and judgments and experiences of subject matter experts. An abductive approach was used to develop a tri-level taxonomy, the Taxonomy of Demands Healthcare Professionals Experience (TDHPE), that categorizes healthcare professionals’ concerns regarding medication and supply shortages, communication, economic stress, workload, organizational support, psychological distress, and society, to name a few. Although the TDHPE was robustly and rigorously developed, machine learning algorithms, specifically IBM Watson’s Natural Language Understanding (NLU) service, were used to replicate human coding. IBM Watson’s NLU service demonstrated a high level of accuracy replicating comments in the superordinate (i.e., large) and basic (i.e., medium) levels of the TDHPE but demonstrated a low level of accuracy replicating comments in the subordinate (i.e., small) level. As predicted, IBM Watson’s NLU service classified comments into the broader categories more accurately than the specific categories of the TDHPE. However, categories in the TDHPE that were generated by IBM Watson’s NLU service were not consistent across healthcare professionals’ roles. Ultimately, the purpose of these strategies is to help those who help other people; to help improve the workplace for our healthcare heroes.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.